Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Nazi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     всё
    -0.08
    쭙
    -0.07
    朸
    -0.07
     Posts
    -0.07
    ❯
    -0.07
    十堰
    -0.07
    心得体会
    -0.07
    希望能够
    -0.06
     POINT
    -0.06
     erre
    -0.06
    POSITIVE LOGITS
     BB
    0.08
     איתו
    0.08
     alarmed
    0.08
     Nazi
    0.08
    bra
    0.07
    蟑
    0.07
    amburger
    0.07
    azi
    0.07
    转基因
    0.07
    젓
    0.07
    Act Density 0.006%

    No Known Activations